deeptools

Pass

Audited by Gen Agent Trust Hub on Nov 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill includes a helper script, scripts/workflow_generator.py, which generates bash scripts based on user-provided inputs and predefined templates. This process involves concatenating user-supplied strings into executable shell commands. To mitigate potential security risks, the script implements robust sanitization, including a whitelist-based regular expression for paths, path traversal checks (forbidding '..'), and shell-quoting using the shlex.quote function for all interpolated variables.
  • [COMMAND_EXECUTION]: The skill is configured to use the Bash tool to perform bioinformatic tasks such as converting BAM files to coverage tracks and calculating quality metrics. These operations are standard for the toolkit's intended scientific use case and are documented across multiple reference files.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for processing untrusted genomic data files (e.g., BAM, BED). The scripts/validate_files.py script reads the initial portions of BED files to ensure format compliance. While this exposes a surface for processing attacker-controlled content, the skill defines clear expectations for data formats and provides validation logic to ensure safe handling of these files.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 8, 2026, 02:07 AM